Policy Gradient vs. Action-value based methods Permalink
An empirical analysis on policy-gradient methods vs. action-value based methods for control
Posts by Collection
portfolio
Reinforcemenet learning with Robotics Permalink
A real-time learning of an off-policy RL control algorithm on a real robot(Create2).
publications
CIFAR-10: KNN-based Ensemble of Classifiers
Published in 2016 International Conference on Computational Science and Computational Intelligence, 2016
This paper studies the performance of different classifiers on the CIFAR-10 dataset, and builds an ensemble of classifiers to reach a better performance.
Download here
VolMap: A Real-time Model for Semantic Segmentation of a LiDAR surrounding view
Published in ICML 2019 - Workshop on AI for Autonomous Driving, 2019
This paper introduces a real-time approach for 3D LiDAR semantic segmentation
Download here
Multi-Sensor Fusion for Radar Cocoon object detection
Published in Germany, 2019
DE Patent DE102019127283.1 A
Safe Evaluation For Offline Learning: Are We Ready To Deploy?
Published in NeurIPS 2021 Workshop on Deployable Decision Making in Embodied Systems [Spotlight], 2021
This paper proposes using high-confidence off-policy evaluation for Offline Reinforcement Learning
Download here
A Framework for Safe Evaluation of Offline Learning
Published in MSc Thesis, University of Alberta, Canada, 2022
My MSc thesis presented a framework for performing safe evaluation of offline learning methods.
Download here
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
CS 106: Fundamentals of Computer Science
Teaching Assistant, The American University in Cairo, Department of Computer Science, 2014
This course covers fundamentals of computer science and basics of programming taught in C++ . My role included helping students through labs and office hours.
Coursera’s Deep Learning Specialization
Instructor, Alama Initiative, Egypt, 2018
I volunteered to teach deep learning concepts for a group of 20 undergrad and grad students taking Coursera’s deep-learning specialization following up with their progress throughout the courses. This was done through a student-run initiative called ‘Alama’.
CMPUT 328: Visual Recognition
Teaching Assistant, University of Alberta, Department of Computing Science, 2019
This course covers computer vision tasks with deep learning, taught with PyTorch. My role included teaching a weekly lab on computer vision with deep learning bascis, and preparing the assignments/ quizzes.
CMPUT 296: Basics of Machine Learning
Teaching Assistant, University of Alberta, Department of Computer Science, 2020
The course tackles the basics of machine learning: material can be found on the website
CMPUT 656: Interactive Machine Learning
Teaching Assistant, University of Alberta, Department of Computer Science, 2020
The course tackles basics of AI and machine learning systems interacting with one or more humans: material can be found on the website
CMPUT 296: Basics of Machine Learning
Teaching Assistant, University of Alberta, Department of Computer Science, 2021
The course tackles the basics of machine learning: material can be found on the website